policies

A security-policy viewing procedure for AgentKeeper, a tool that checks coding-agent activity for risky behavior. It reports whether detection is local or connected and lists blocked tools, commands, paths, and threat patterns.

In plain words
What is it for?
Reviewing AgentKeeper’s security mode, restrictions, and checks for threats such as credential theft, destructive deletion, reverse shells, and prompt injection.
Why use it?
It shows which safety checks are active before you rely on the tool to block dangerous actions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/rad-security/claude-code-plugin/policies
Any agent
npx skills add rad-security/claude-code-plugin --skill policies
Clone the repo
git clone --depth 1 https://github.com/rad-security/claude-code-plugin

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.01168
Opus 5 $0.00025 $0.00584
Sonnet 5 $0.00010 $0.00234
Haiku 4.5 $0.00005 $0.00117

Measured 2d ago against content hash 3db3281b329f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

policies scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- recursive_delete_root — rm -rf / and system directory wipes

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s --max-time 5 "https://www.agentkeeper.dev/api/v1/claude-code/policies" \
plugins/agentkeeper/skills/policies/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentKeeper Policies

You are displaying the organization's AgentKeeper security policies.

Step 1: Check Connection Mode

AGENTKEEPER_DIR="$HOME/.agentkeeper-plugin"
[ -n "$CLAUDE_PLUGIN_DATA" ] && AGENTKEEPER_DIR="$CLAUDE_PLUGIN_DATA"
cat "$AGENTKEEPER_DIR/api_key" 2>/dev/null

If no API key (local mode):

Display:

AgentKeeper Policies

Mode: Local (no account connected)

Running with default detection patterns. In local mode, AgentKeeper uses
a bundled set of 12 critical/high threat patterns:

  - credential_exfil — SSH keys, AWS creds, env files sent to network
  - reverse_shell — bash/python/nc reverse shell patterns
  - recursive_delete_root — rm -rf / and system directory wipes
  - dns_exfil — data exfiltration via DNS
  - system_file_write — writing to /etc, /usr, /System
  - ssh_config_write — modifying authorized_keys, SSH config
  - cryptominer — cryptocurrency mining patterns
  - startup_injection — modifying .bashrc, .zshrc, LaunchAgents
  - cicd_tampering — modifying GitHub Actions, GitLab CI
  - suid_manipulation — setting SUID bits
  - prompt_injection — common injection patterns in prompts
  - token_theft — stealing auth tokens and session data

Default behavior: warn (detect and flag, but allow execution)

To view and manage organization policies, connect an account:
  /agentkeeper:connect

Pro plan adds:
  - Custom blocked tool lists
  - Custom blocked command patterns
  - Path restriction policies
  - Custom blocklists (words, domains, patterns)
  - Policy enforcement across all team workstations

Stop here if local mode.

If API key exists (connected mode):

Proceed to Step 2.

Step 2: Fetch Policies

Fetch shield policy

AGENTKEEPER_DIR="$HOME/.agentkeeper-plugin"
[ -n "$CLAUDE_PLUGIN_DATA" ] && AGENTKEEPER_DIR="$CLAUDE_PLUGIN_DATA"
API_KEY=$(cat "$AGENTKEEPER_DIR/api_key")
curl -s --max-time 5 "https://www.agentkeeper.dev/api/v1/claude-code/policies" \
  -H "Authorization: Bearer $API_KEY"

If the endpoint returns an error or is not found, try the shield policies endpoint:

AGENTKEEPER_DIR="$HOME/.agentkeeper-plugin"
[ -n "$CLAUDE_PLUGIN_DATA" ] && AGENTKEEPER_DIR="$CLAUDE_PLUGIN_DATA"
API_KEY=$(cat "$AGENTKEEPER_DIR/api_key")
curl -s --max-time 5 "https://www.agentkeeper.dev/api/v1/shield/policies" \
  -H "Authorization: Bearer $API_KEY"

Read the full file on GitHub · 161 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 161 lines · 50 tokens per session scan B 3db3281b329f

Subscribe to this mod's changes

policies is a skill published in the GitHub repository rad-security/claude-code-plugin (2 stars, last pushed 26d ago), licensed MIT. It adds 50 tokens to every session and 1,168 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens